© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1306
    Prev
    Next
    INDEX
    Explanations

    numbers followed by commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alfo
    -1.88
     moy
    -1.84
     royale
    -1.81
    獁
    -1.76
    牁
    -1.70
     estadounid
    -1.66
     tod
    -1.64
     forbindelse
    -1.62
     ordf
    -1.60
    ㈰
    -1.60
    POSITIVE LOGITS
     and
    1.90
     —
    1.89
    又能
    1.65
     you
    1.62
    把我
    1.61
    倏
    1.61
     who
    1.60
    ка
    1.59
     하고
    1.58
    reactstrap
    1.58
    Activations Density 0.035%

    No Known Activations